Blog Archives

A big problem in our community

December 14, 2017
By
A big problem in our community

Hi all, Kristian Lum, who was already one of my Statistics superheroes for her many interesting papers and great talks, bravely wrote the following text about her experience as a young statistician going to conferences: https://medium.com/@kristianlum/statistics-we-have-a-problem-304638dc5de5 I can’t thank Kristian enough for speaking out. Her experience is both shocking and hardly surprising. Many, many academics […]

Read more »

nrow, references and copies

December 10, 2017
By
nrow, references and copies

    Hi all, This post deals with a strange phenomenon in R that I have noticed while working on unbiased MCMC. Reducing the problem to a simple form, consider the following code, which iteratively samples a vector ‘x’ and stores it in a row of a large matrix called ‘chain’ (I’ve kept the MCMC […]

Read more »

Bayesian model comparison with vague or improper priors

November 6, 2017
By
Bayesian model comparison with vague or improper priors

  Hi, With Stephane Shao, Jie Ding and Vahid Tarokh we have just arXived a tech report entitled “Bayesian model comparison with the Hyvärinen score: computation and consistency“. Here I’ll explain the context, that is, scoring rules and Hyvärinen scores (originating in Hyvärinen’s score matching approach to inference), and then what we actually do in the paper. Let’s […]

Read more »

Approximating the cut distribution

October 1, 2017
By
Approximating the cut distribution

Hi, This post is about computational issues with the cut distribution for Bayesian inference in misspecified models. Some motivation was given in a previous post about a recent paper on modular Bayesian inference. The cut distribution, or variants of it, might play an important role in combining statistical models, especially in settings where one wants to propagate uncertainty […]

Read more »

Unbiased Hamiltonian Monte Carlo with couplings

September 17, 2017
By
Unbiased Hamiltonian Monte Carlo with couplings

With Jeremy Heng we have recently arXived a paper describing how to remove the burn-in bias of Hamiltonian Monte Carlo (HMC). This follows a recent work on unbiased MCMC estimators in general on which I blogged here. The case of HMC requires a specific yet very simple coupling. A direct consequence of this work is that Hamiltonian Monte […]

Read more »

Statistical learning in models made of modules

September 9, 2017
By
Statistical learning in models made of modules

    Hi, With Lawrence Murray, Chris Holmes and Christian Robert, we have recently arXived a paper entitled “Better together? Statistical learning in models made of modules”. Christian blogged about it already. The context is the following: parameters of a first model appear as inputs in another model. The question is whether to consider a “joint model […]

Read more »

Sampling from a maximal coupling

September 5, 2017
By
Sampling from a maximal coupling

  Hi, In a recent work on parallel computation for MCMC, and also in another one, and in fact also in an earlier one, my co-authors and I use a simple yet very powerful object that is standard in Probability but not so well-known in Statistics: the maximal coupling. Here I’ll describe what this is […]

Read more »

Update on inference with Wasserstein distances

August 15, 2017
By
Update on inference with Wasserstein distances

Hi again, As described in an earlier post, Espen Bernton, Mathieu Gerber and Christian P. Robert and I are exploring Wasserstein distances for parameter inference in generative models. Generally, ABC and indirect inference are fun to play with, as they make the user think about useful distances between data sets (i.i.d. or not), which is sort of implicit in classical […]

Read more »

Unbiased MCMC with couplings

August 14, 2017
By
Unbiased MCMC with couplings

    Hi, With John O’Leary and Yves Atchadé , we have just arXived our work on removing the bias of MCMC estimators. Here I’ll explain what this bias is about, and the benefits of removing it. What bias? An MCMC algorithm defines a Markov chain , with stationary distribution , so that time averages of the chain […]

Read more »

Particle methods in Statistics

June 30, 2017
By
Particle methods in Statistics

Hi there, In this post, just in time for the summer, I propose a reading list for people interested in discovering the fascinating world of particle methods, aka sequential Monte Carlo methods, and their use in statistics. I also take the opportunity to advertise the SMC workshop in Uppsala (30 Aug – 1 Sept), which […]

Read more »


Subscribe

Email:

  Subscribe